<ul><li>Researchers have introduced the Spiking Dynamic Graph Network (SDGN) for modeling and predicting temporal point processes (TPPs).</li><li>SDGN leverages the temporal processing capabilities of spiking neural networks (SNNs) and spike-timing-dependent plasticity (STDP) to dynamically estimate underlying spatio-temporal functional graphs.</li><li>Unlike existing methods, SDGN adapts to any dataset by learning dynamic spatio-temporal dependencies directly from the event data, enhancing generalizability and robustness.</li><li>Evaluations on synthetic and real-world datasets show that SDGN achieves superior predictive accuracy while maintaining computational efficiency.</li></ul>

Dynamic Graph Structure Estimation for Learning Multivariate Point Process using Spiking Neural Networks

Discover more